LATIDIA · Robótica

CPNav: Navegación Visión-Lenguaje Calibrada para la Búsqueda de Objeto-Objetivo en Entornos Invisibles

arXiv:2611.10366v1 Tipo de anuncio: nuevo Resumen: Dirigir un robot para localizar un objeto objetivo en entornos invisibles sigue siendo un desafío central en la IA incorporada. Los métodos basados en el Modelo de Visión y Lenguaje (VLM) proporcionan una rica

La noticia

arXiv:2611.10366v1 Announce Type: new Abstract: Directing a robot to locate a target object in unseen environments remains a central challenge in embodied AI. Vision-Language Model (VLM)-based methods provide rich semantic reasoning but often produce uncalibrated and overconfident action decisions. We introduce CPNav, a navigation framework that combines collision-aware planning with statistically calibrated VLM action scoring for map-free object-goal navigation. From RGB-D input, CPNav constructs a navigability map, generates collision-free motion primitives, and queries two VLMs for goal detection and action scoring. The resulting scores are calibrated offline via conformal prediction (CP) using oracle actions obtained through a tree-structured exploration procedure with backtracking, providing finite-sample guarantees at a user-specified risk level.